Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-02 11:01:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	CMakeLists.txt
#	README.md
#	ci/run.sh
#	docs/BLIS.md
#	flake.lock
#	grammars/README.md
This commit is contained in:
Concedo
2024-05-08 09:58:23 +08:00
parent 3eeb4bc127 c780e75305
commit bc39b4d98a
15 changed files with 94 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
llama.cpp
+4
View File
@@ -4443,6 +4443,9 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "command-r") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_COMMAND_R;
} else if (
tokenizer_pre == "olmo") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_OLMO;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@@ -12539,6 +12542,7 @@ struct llm_tokenizer_bpe {
});
break;
case LLAMA_VOCAB_PRE_TYPE_GPT2:
case LLAMA_VOCAB_PRE_TYPE_OLMO:
word_collection = unicode_regex_split(text, {
"'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
});